Despite the benefits of minimally invasive surgery, interventions such as laparoscopic liver surgery present unique challenges, like the significant anatomical differences between preoperative images and intraoperative scenes due to pneumoperitoneum, patient pose, and organ manipulation by surgical instruments. To address these challenges, we propose a method for intraoperative 3D reconstruction of the surgical scene, including vessels and tumors, without altering the surgical workflow. The technique combines Neural Radiance Field (NeRF) reconstructions from tracked laparoscopic videos with ultrasound 3D compounding. We evaluate the accuracy of our reconstructions on a clinical laparoscopic liver ablation dataset, consisting of laparoscope and patient reference poses from optical tracking, laparoscopic and ultrasound videos, as well as preoperative and intraoperative CTs. We propose a solution to compensate for liver deformations due to pressure applied during ultrasound acquisitions, improving the overall accuracy of the 3D reconstructions compared to the ground truth intraoperative CT with pneumoperitoneum. We train a unified NeRF from the ultrasound and laparoscope data, which allows real-time view synthesis providing surgeons with comprehensive intraoperative visual information for laparoscopic liver surgery.

not-yet-known not-yet-known not-yet-known unknown Deep learning models are used to minimize the number of polyps that goes unnoticed by the experts and to accurately segment the detected polyps during interventions. Although state-of-the-art models are proposed, it remains a challenge to define representations that are able to generalize well and that mediate between capturing low-level features and higher-level semantic details without being redundant. Another challenge with these models is that they are computation and memory intensive, which can pose a problem with real-time applications. To address these problems, we propose PlutoNet for polyp segmentation which requires only 9 FLOPs and 2,626,537 parameters, less than 10% of the parameters required by its counterparts. With PlutoNet, we propose a novel decoder consistency training approach that consists of a shared encoder, the modified partial decoder, which is a combination of the partial decoder and full-scale connections that capture salient features at different scales without redundancy, and the auxiliary decoder which focuses on higher-level semantic features. We train the modified partial decoder and the auxiliary decoder with a combined loss to enforce consistency, which helps strengthen learned representations. We perform ablation studies and experiments which show that PlutoNet performs significantly better than the state-of-the-art models, particularly on unseen datasets.

In percutaneous pelvic trauma surgery, accurate placement of Kirschner wires(K-wires) is crucial to ensure effective fracture fixation and avoid complications due to breaching the cortical bone along an unsuitable trajectory. Surgical navigation via mixed reality(MR) can help achieve precise wire placement in a low-profile form factor. Current approaches in this domain are as yet unsuitable for real-world deployment because they fall short of guaranteeing accurate visual feedback due to uncontrolled bending of the wire. To ensure accurate feedback, we introduce StraightTrack, an MR navigation system designed for percutaneous wire placement in complex anatomy. StraightTrack features a marker body equipped with a rigid access cannula that mitigates wire bending due to interactions with soft tissue and a covered bony surface. Integrated with an Optical See-Through Head-Mounted Display (OST HMD capable of tracking the cannula body, StraightTrack offers real-time 3D visualization and guidance without external trackers. In phantom experiments with two experienced orthopedic surgeons, StraightTrack improves wire placement accuracy, achieving the ideal trajectory within 5.26 ± 2.29 mm and 2.88 ±1.49°, compared to over 12.08 mm and 4.07° for comparable methods. As MR navigation systems continue to mature, StraightTrack realizes their potential for internal fracture fixation and other percutaneous orthopedic procedures.

The estimation of the pose of surgical instruments is important in Robot-assisted Minimally Invasive Surgery (RMIS) to assist surgical navigation and enable autonomous robotic task execution. The performance of current instrument pose estimation methods deteriorates significantly in the presence of partial tool visibility, occlusions, and changes in the surgical scene. In this work, a vision-based framework is proposed for markerless estimation of the 6DoF pose of surgical instruments. To deal with partial instrument visibility, a keypoint object representation is used and stable and accurate instrument poses are computed using a PnP solver. To boost the learning process of the model under occlusion, a new mask-based data augmentation approach has been proposed. To validate our model, a dataset for instrument pose estimation with highly accurate ground truth data has been generated using different surgical robotic instruments. The proposed network can achieve submillimeter accuracy and our experimental results verify its generalisability to different shapes of occlusion.

A novel approach is proposed in this paper to reconstruct the far-field radiation pattern from the phaseless electric field of an antenna scanned on a single near-field sphere. It adopts the dipole equivalence approach to project the near-field electric field into a spherically distributed array of electric dipoles. We introduce a term representing the residue from the linearly correlated portion in the least-square problem associated with the dipole equivalence, namely the linear correlation residue (LCR). It is demonstrated that by iterative search to minimize the LCR using the Covariance Matrix Adaptation Evolution Strategy (CMA-ES), near-field phase distributions can be found efficiently from the magnitude-only near-field, and the far-field radiation pattern can be computed. Two representative case studies are given here to validate the proposed method. Results demonstrate good agreements between computations and simulations.

Intelligent identification of road vehicles in a densely populated country like Bangladesh is challenging due to irregular traffic patterns, highly diverse vehicle types, and a cluttered environment. This study proposes a system that utilizes computer vision technology to identify road vehicles with greater speed and accuracy. Firstly, dataset was collected and organized in Roboflow to identify 21 classes of Bangladeshi native vehicle images, along with two additional classes for people and animals. Subsequently, YOLOv5 model underwent training on the dataset. This process produced bounding boxes, which were then refined using NMS technique. The loss function CIoU is employed to obtain the accurate regression bounding box of the vehicles. MS CO-CO dataset weights are included in the YOLOv5 deep learning network for transfer learning. Finally, Python TensorBoard was used to evaluate and visualize the model’s performance. The model was developed and validated on Google Colab platform. A set of experimental evaluations demonstrate that the proposed method is effective and efficient in recognizing Bangladeshi Vehicles. In all test road scenarios, the proposed computer vision system for road vehicle identification achieved 95.8% accuracy and 0.3ms processing time for 200 epochs. This research could lead to intelligent transportation systems and driverless vehicles in Bangladesh.

High Resolution Range Profiles (HRRP) have become a key area of focus in the domain of Radar Automatic Target Recognition (RATR). Despite the success of deep learning based HRRP recognition, these methods needs a large amount of training samples to generate good performance, which could be a severe challenge under non-cooperative circumstances. Currently, deep learning based models treat HRRP as sequences, which may lead to ignorance of the internal relationship of range cells. This letter introduces HRRPGraphNet, whose pivotal innovation is the transformation of HRRP data into a novel graph structure, utilizing a range cell amplitude-based node vector and a range-relative adjacency matrix. This graph-based approach facilitates both local feature extraction via one-dimensional convolution layers, global feature extraction through a graph convolution layer and a attention module. Experiments on the aircraft electromagnetic simulation dataset confirmed HRRPGraphNet’s superior accuracy and robustness, particularly in limited training sample environments, underscoring the potential of graph-driven innovations in HRRP-based RATR. Codes are available at: https://github.com/MountainChenCad/HRRPGraphNet.

A document by Anzhan Liu. Click on the document to view its contents.

The current overhead work robot for transmission line faces issues related to its compact structure and high target localization requirements. To address these challenges, this paper proposes a lightweight bolt detection algorithm based on improved YOLOv8 (You Only Look Once v8) model. Firstly, the C2f module in the feature extraction network is integrated with the Self-Calibrated Convolution (SCConv) module, and the model is streamlined by reducing spatial and channel redundancies of the network through the SRU and CUR mechanisms in the module. Secondly, the P2 Small Object Detection Layer is introduced into the neck structure and the BiFPN network structure is incorporated to enhance the bidirectional connection paths, thereby promoting the upward and downward propagation of features. It improves the accuracy of the network for bolt-small target detection. The experimental results show that, compared to the original YOLOv8 model, the proposed algorithm demonstrates superior performance on a self-collected dataset. In this paper, the mAP accuracy is improved by 9.9%, while the number of model parameters and the model size is reduced by 0.973×106 and 1.7MB, respectively. The improved algorithm improves the accuracy of the bolt detection while reducing the computation complexity to achieve more lightweight model.

This brief investigates the multi-point fault repair problem in active distribution networks, establishing resilience assessment metrics and constructing a fault repair mathematical model with road network coupling. An improved genetic algorithm is proposed, utilizing a comparison crossover operator and population information entropy. Compared to traditional algorithms, the comparison crossover operator preserves high-quality genes, while population information entropy maintains diversity, preventing the algorithm from converging on local optima. Simulation analysis demonstrates that the proposed fault repair method can restore normal power supply to distribution network lines within a short period and offers significant advantages in fault repair tasks.

In this paper, we tackle the challenging problem of multi-target cross localization within a novel distributed high-frequency surface wave radar (HFSWR). This system consists two transmitter-receiver pairs, each of which can correspondingly generate a set of Range-Doppler measurements. By associating the Range-Doppler measurements from the same target, the individual target location can be derived using the associated measurements. However, when multiple targets are involved, it is unknown which measurements originate from the same target, leading to ambiguities in the measurement-to-measurement association. False associations can result in the ghosts, ultimately degrading the overall system performance. To deal with the ghosts, we propose a three-stage deghosting method that incorporates the geometric characteristics of the system, the velocity features of the targets and the motion features of the targets across multiple frames. ̵‌The simulation results demonstrate the effectiveness of our proposed method compared with the other investigated deghosting algorithms. Our proposed approach exhibits robust target detection capability while significantly reducing both the OSPA error and the cardinality error.

This paper introduces a novel resource allocation algorithm, Priority-Aware Federated Resource Allocation (PAFRA), tailored for Power Line Communication (PLC) systems. Utilizing a federated learning framework, PAFRA optimizes the distribution of limited spectrum resources among multiple nodes within a residential environment. The algorithm employs a priority-based time slot allocation to manage subchannel conflicts and uses a Double Deep Q-Network (DDQN) for local training at each node, incorporating state, action, and reward configurations to refine transmission power and subchannel selections. Extensive simulations demonstrate that PAFRA significantly enhances system throughput across various Signal-to-Noise Ratio (SNR) levels, outperforming existing adaptive resource allocation strategies and random allocation methods. The findings highlight PAFRA’s ability to achieve superior performance in dynamic PLC environments, illustrating its potential to optimize network efficiency while adhering to strict regulatory emission standards.

Condition monitoring data can be used to assess the health of a power system component but is rarely used to assess the reliability of the power system they are part of. For high-voltage circuit breakers (HVCBs), the susceptibility to various failures can be assessed by examining trip coil current (TCC) measurements. HVCBs have two failure modes, failure to trip on command and tripping without a command, which are triggered by various failure mechanisms that in turn may depend on the technical condition of the HVCBs. The aim of this paper is to demonstrate a methodology for quantifying the impact that the technical condition of HVCBs has on the power system reliability indices. An equivalent transmission line failure rate considering protection system failures, including failures related to HVCBs, can be calculated by computing contributions from various fault types (FTs). This paper proposes a framework that can quantify the frequency of the FTs that are affected by HVCB condition. The system-level effects are then evaluated using approximate methods for power system reliability evaluation. To demonstrate the principles and benefits of this methodology, a case study is presented that incorporates HVCB condition data from the Icelandic transmission grid into an illustrative 4-bus test system; a dataset of 83 TCC measurements from 38 HVCBs from the Icelandic Transmission System Operator is used, together with an outage database of life histories of 464 HVCBs from the Icelandic transmission grid. Results indicate that the condition deterioration associated with the probability of an HVCB failing to trip on command can significantly degrade the reliability indices.

Characterizing soil moisture (SM) around drip irrigation pipes is crucial for precise and optimized farming. Machine learning (ML) approaches are particularly suitable for this task as they can reduce uncertainties caused by soil conditions and the drip pipe positions, using features extracted from relevant datasets. This letter addresses local moisture detection in the vicinity of dripping pipes using a portable microwave imaging system. The employed ML approach is fed with two dimensional images generated by two different microwave imaging techniques based on spatio-temporal measurements at various frequency bands. The study investigates the performance of K-Nearest Neighbor (KNN) and Convolutional Neural Networks (CNN) algorithms for moisture classification based on these images in three scenarios: before clutter removal, after clutter removal, and after applying imaging techniques such as back projection and the Born approximation. We also explore the potentials of CNN and KNN for moisture estimation around the plant roots and in the presence of pebbles. The results demonstrate the more accurate moisture estimation using CNN when it is applied after clutter reduction considering back projection algorithm (BPA) as the imaging technique. The results indicate that using the Back Projection technique for image formation, combined with CNN for classification, improves leak detection accuracy by approximately 20% compared to other methods.

The operating environment of transformers is getting more complex with the emergence of new energy sources and power electronic devices. This complexity can cause minor internal faults in transformer windings. Under the cumulative effect, minor faults gradually develop into serious faults, resulting in transformer damage. Conventional differential protection systems may have difficulty detecting these glitches and require avoiding the problem of protection false activation caused by inrush currents. This paper proposes a new online monitoring method for transformer windings based on longitudinal branch circuit conductance to address this issue. First, a unified transformer equivalent circuit is proposed to represent transformers under normal conditions, inrush currents, and internal faults. Then, an online transformer monitoring method based on branch conductance is proposed, which is immune to inrush currents. This method aims to prevent delayed detection of faults during inrush currents, improving sensitivity and response speed, especially for minor turn-to-turn faults hidden in inrush currents. The proposed method also provides higher sensitivity to minor turn-to-turn faults and larger protection margins. Simulation and experimental results validate the effectiveness of this method.

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental disorder with a strong genetic component. This research work aims to identify key genes associated with ASD using a hybrid deep learning approach To identify influential/key genes associated with ASD, a protein-protein interaction (PPI) network is constructed, and a Graph Convolutional Network (GCN), a deep learning method, is employed. The GCN extracts features from the network structure based on gene interactions. Subsequently, Logistic Regression (LR) leverages these features to classify genes into influential and non-influential categories. The LR is chosen for its effectiveness in binary classification and ability to reveal feature importance, providing valuable insights into the underlying genetic mechanisms of ASD. Additionally, a simulation using the Susceptible-Infected (SI) model is conducted to calculate the infection ability of influential genes. This simulation demonstrates the higher infection ability of the genes identified by the proposed method, highlighting its effectiveness in pinpointing key genetic factors associated with ASD. Also, the result compared with existing centrality methods. The proposed method performs better to identify key genes involve in ASD. Our proposed method outperforms traditional measures in identifying key genes in the network, offering potential applications for identifying biomarkers. This innovative approach aligns with advancements in therapeutic and diagnostic systems, healthcare information systems, and neural engineering, providing a robust framework for future ASD research and potential applications in other neurodevelopmental disorders.

This study developed a damped alternating current (DAC) testing methodology, composed of an improved DAC generator and a pulse-based distributed PD-detection technique. The improved DAC generator lacks high voltage (HV) solid-state switches and is thus a cost-efficient solution for field-testing voltage generation via a direct current–alternating current (DC-AC) conversion technique. A capacitor bank is used for power supply to achieve the requirement for high instantaneous power. In addition, the use of a distributed PD detection technique enables high sensitivity and makes the method free from restrictions of the cable length. To reduce the construction cost of the distributed PD-detection system, a pulse synchronization technique is used. Attempts was made to reduce the weight based on the simulations, and a prototype with the total weight of 850kg was designed and developed for a 64/110kV power cable. Laboratory and field tests validated the effectiveness of the cost-efficient DAC testing methodology.

Faults in power systems occur for various reasons, such as aging or natural disasters. Detecting, locating, and promptly clearing these faults is crucial for maintaining the safety and reliability of transmission lines. Distance relays, which protect transmission lines, detect faults, estimate their location, and send the required commands. However, these relays may experience mis-detection due to manipulated impedance arising from both internal and external factors. These factors include measurement device errors, network topology changes, the presence of fault resistance, and injected currents from remote line terminals. To address this challenge, we propose an innovative adaptive protection scheme that considers fault resistance, changes in network topology, and injected current from the opposite end of the line. By estimating the equivalent circuit impedances of the network connected to the terminal of the transmission line, this protection scheme utilizes impedance estimation techniques at the line terminals and offline network information. Simulation studies (tested on the IEEE 39-bus standard network) show that the proposed scheme accurately estimates fault location and fault resistance with high precision. The simulation results demonstrate its effectiveness in improving the performance of conventional distance protection relays in both the first and second protection zones (Z_1 and Z_2).